rov-offline/rule_rank_day_by_30day.py

import pandas as pd
import math
from functools import reduce
from odps import ODPS
from threading import Timer
from datetime import datetime, timedelta
from get_data import get_data_from_odps
from db_helper import RedisHelper
from utils import filter_video_status, check_table_partition_exits
from config import set_config
from log import Log

config_, _ = set_config()
log_ = Log()

features = [
    'apptype',
    'videoid',
    'preview人数',  # 过去24h预曝光人数
    'view人数',  # 过去24h曝光人数
    'play人数',  # 过去24h播放人数
    'share人数',  # 过去24h分享人数
    '回流人数',  # 过去24h分享，过去24h回流人数
    'preview次数',  # 过去24h预曝光次数
    'view次数',  # 过去24h曝光次数
    'play次数',  # 过去24h播放次数
    'share次数',  # 过去24h分享次数
    'platform_return',
    'platform_preview',
    'platform_preview_total',
    'platform_show',
    'platform_show_total',
    'platform_view',
    'platform_view_total',
]


def data_check(project, table, now_date):
    """检查数据是否准备好"""
    odps = ODPS(
        access_id=config_.ODPS_CONFIG['ACCESSID'],
        secret_access_key=config_.ODPS_CONFIG['ACCESSKEY'],
        project=project,
        endpoint=config_.ODPS_CONFIG['ENDPOINT'],
        connect_timeout=3000,
        read_timeout=500000,
        pool_maxsize=1000,
        pool_connections=1000
    )

    try:
        dt = datetime.strftime(now_date, '%Y%m%d')
        check_res = check_table_partition_exits(date=dt, project=project, table=table)
        if check_res:
            sql = f'select * from {project}.{table} where dt = {dt}'
            with odps.execute_sql(sql=sql).open_reader() as reader:
                data_count = reader.count
        else:
            data_count = 0
    except Exception as e:
        data_count = 0
    return data_count


def get_feature_data(now_date, project, table):
    """获取特征数据"""
    dt = datetime.strftime(now_date, '%Y%m%d')
    records = get_data_from_odps(date=dt, project=project, table=table)
    feature_data = []
    for record in records:
        item = {}
        for feature_name in features:
            item[feature_name] = record[feature_name]
        feature_data.append(item)
    feature_df = pd.DataFrame(feature_data)
    return feature_df


def cal_score(df, param):
    # score计算公式: score = share次数/(view+1000)+0.01*return/(share次数+100)
    df = df.fillna(0)
    if param.get('view_type', None) == 'video-show':
        df['share_rate'] = df['share次数'] / (df['platform_show'] + 1000)
    elif param.get('view_type', None) == 'preview':
        df['share_rate'] = df['share次数'] / (df['preview人数'] + 1000)
    else:
        df['share_rate'] = df['share次数'] / (df['view人数'] + 1000)
    df['back_rate'] = df['回流人数'] / (df['share次数'] + 100)
    df['score'] = df['share_rate'] + 0.01 * df['back_rate']
    df['platform_return_rate'] = df['platform_return'] / df['回流人数']
    df = df.sort_values(by=['score'], ascending=False)
    return df


def video_rank_h(df, now_date, rule_key, param, data_key):
    """
    获取符合进入召回源条件的视频，与每日更新的rov模型结果视频列表进行合并
    :param df:
    :param now_date:
    :param rule_key: 天级规则数据进入条件
    :param param: 天级规则数据进入条件参数
    :param data_key: 使用数据标识
    :return:
    """
    redis_helper = RedisHelper()
    log_.info(f"videos_count = {len(df)}")

    # videoid重复时，保留分值高
    df = df.sort_values(by=['score'], ascending=False)
    df = df.drop_duplicates(subset=['videoid'], keep='first')
    df['videoid'] = df['videoid'].astype(int)

    day_recall_videos = df['videoid'].to_list()
    log_.info(f'day_by30day_recall videos count = {len(day_recall_videos)}')

    # 视频状态过滤
    filtered_videos = filter_video_status(day_recall_videos)
    log_.info('filtered_videos count = {}'.format(len(filtered_videos)))

    # 获取top视频
    top = param.get('top')
    day_recall_df = df[df['videoid'].isin(filtered_videos)]
    day_recall_df = day_recall_df.sort_values(by=['score'], ascending=False)
    day_recall_df = day_recall_df[:top]

    # 写入对应的redis
    now_dt = datetime.strftime(now_date, '%Y%m%d')
    day_video_ids = []
    day_recall_result = {}
    for video_id in day_recall_df['videoid'].to_list():
        score = day_recall_df[day_recall_df['videoid'] == video_id]['score']
        day_recall_result[int(video_id)] = float(score)
        day_video_ids.append(int(video_id))

    day_30day_recall_key_name = f"{config_.RECALL_KEY_NAME_PREFIX_30DAY}{data_key}:{rule_key}:{now_dt}"

    if len(day_recall_result) > 0:
        log_.info(f"count = {len(day_recall_result)}, key = {day_30day_recall_key_name}")
        redis_helper.add_data_with_zset(key_name=day_30day_recall_key_name, data=day_recall_result,
                                        expire_time=2 * 24 * 3600)


def merge_df(df_left, df_right):
    """
    df按照videoid 合并，对应特征求和
    :param df_left:
    :param df_right:
    :return:
    """
    df_merged = pd.merge(df_left, df_right, on=['videoid'], how='outer', suffixes=['_x', '_y'])
    df_merged.fillna(0, inplace=True)
    feature_list = ['videoid']
    for feature in features:
        if feature in ['apptype', 'videoid']:
            continue
        df_merged[feature] = df_merged[f'{feature}_x'] + df_merged[f'{feature}_y']
        feature_list.append(feature)
    return df_merged[feature_list]


def merge_df_with_score(df_left, df_right):
    """
    df 按照videoid合并，平台回流人数、回流人数、分数 分别求和
    :param df_left:
    :param df_right:
    :return:
    """
    df_merged = pd.merge(df_left, df_right, on=['videoid'], how='outer', suffixes=['_x', '_y'])
    df_merged.fillna(0, inplace=True)
    feature_list = ['videoid', '回流人数', 'platform_return', 'score']
    for feature in feature_list[1:]:
        df_merged[feature] = df_merged[f'{feature}_x'] + df_merged[f'{feature}_y']
    return df_merged[feature_list]


def rank(now_date, rule_params, project, table):
    # 获取特征数据
    feature_df = get_feature_data(now_date=now_date, project=project, table=table)
    feature_df['apptype'] = feature_df['apptype'].astype(int)
    # rank
    data_params_item = rule_params.get('data_params')
    rule_params_item = rule_params.get('rule_params')

    for param in rule_params.get('params_list'):
        score_df_list = []
        data_key = param.get('data')
        data_param = data_params_item.get(data_key)
        log_.info(f"data_key = {data_key}, data_param = {data_param}")
        rule_key = param.get('rule')
        rule_param = rule_params_item.get(rule_key)
        log_.info(f"rule_key = {rule_key}, rule_param = {rule_param}")
        merge_func = rule_param.get('merge_func', 1)

        if merge_func == 2:
            for apptype, weight in data_param.items():
                df = feature_df[feature_df['apptype'] == apptype]
                # 计算score
                score_df = cal_score(df=df, param=rule_param)
                score_df['score'] = score_df['score'] * weight
                score_df_list.append(score_df)
            # 分数合并
            df_merged = reduce(merge_df_with_score, score_df_list)
            # 更新平台回流比
            df_merged['platform_return_rate'] = df_merged['platform_return'] / df_merged['回流人数']
            video_rank_h(df=df_merged, now_date=now_date, rule_key=rule_key, param=rule_param, data_key=data_key)

        else:
            df_list = [feature_df[feature_df['apptype'] == apptype] for apptype, _ in data_param.items()]
            df_merged = reduce(merge_df, df_list)
            score_df = cal_score(df=df_merged, param=rule_param)
            video_rank_h(df=score_df, now_date=now_date, rule_key=rule_key, param=rule_param, data_key=data_key)


def rank_bottom(now_date, rule_params):
    """未按时更新数据，用前一天数据作为当前的数据"""
    redis_helper = RedisHelper()
    redis_dt = datetime.strftime(now_date - timedelta(days=1), '%Y%m%d')
    key_prefix_list = [config_.RECALL_KEY_NAME_PREFIX_30DAY]

    for param in rule_params.get('params_list'):
        data_key = param.get('data')
        rule_key = param.get('rule')
        log_.info(f"data_key = {data_key}, rule_key = {rule_key}")
        for key_prefix in key_prefix_list:
            key_name = f"{key_prefix}{data_key}:{rule_key}:{redis_dt}"
            initial_data = redis_helper.get_all_data_from_zset(key_name=key_name, with_scores=True)
            if initial_data is None:
                initial_data = []
            final_data = dict()
            for video_id, score in initial_data:
                final_data[video_id] = score
            # 存入对应的redis
            final_key_name = \
                f"{key_prefix}{data_key}:{rule_key}:{datetime.strftime(now_date, '%Y%m%d')}"
            if len(final_data) > 0:
                redis_helper.add_data_with_zset(key_name=final_key_name, data=final_data, expire_time=2 * 24 * 3600)


def timer_check():
    project = config_.PROJECT_30DAY_APP_TYPE
    table = config_.TABLE_30DAY_APP_TYPE
    rule_params = config_.RULE_PARAMS_30DAY_APP_TYPE
    now_date = datetime.today()
    log_.info(f"now_date: {datetime.strftime(now_date, '%Y%m%d')}")
    now_h = datetime.now().hour
    # 查看当前天级更新的数据是否已准备好
    data_count = data_check(project=project, table=table, now_date=now_date)
    if data_count > 0:
        log_.info(f'day_by30day_data_count = {data_count}')
        # 数据准备好，进行更新
        rank(now_date=now_date, rule_params=rule_params, project=project, table=table)
    elif now_h > 3:
        log_.info('day_by30day_recall data is None!')
        rank_bottom(now_date=now_date, rule_params=rule_params)
    else:
        # 数据没准备好，5分钟后重新检查
        Timer(5 * 60, timer_check).start()


if __name__ == '__main__':
    timer_check()